Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 129252
    Prev
    Next
    INDEX
    Explanations

    roads

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Record
    -0.08
    izzly
    -0.07
     Medium
    -0.07
     Latvia
    -0.07
    PASS
    -0.07
    /lg
    -0.06
     certificate
    -0.06
     Apartment
    -0.06
     Amend
    -0.06
    isEqualTo
    -0.06
    POSITIVE LOGITS
    .]
    0.06
    662
    0.06
    .SetFloat
    0.06
    .lwjgl
    0.06
    *)&
    0.06
    sizeof
    0.06
     __(
    0.06
    (Int
    0.06
     diversified
    0.06
    иф
    0.06
    Activations Density 0.036%

    No Known Activations